A neural network approach to predicting stock exchange movements using external factors

O’Connor, Niall; Madden, Michael G.

doi:10.1016/j.knosys.2005.11.015

Cited by 84 publications

(11 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The forecasting ability of the Neural Networks has attracted the attention of researchers since last two decades and a vast repository of literature is present which provide evidence of the significant forecasting ability of ANN in stock markets. The earlier studies concentrated on the stock market indices and applied numerous technical and financial variables to open the research vistas for ANN in capital markets forecasting (see for example, Armano, Marchesi, & Murru, 2005;Gonzalez Miranda & Burgess, 1997;Lendasse, de Bodt, Wertz, & Verleysen, 2000;Majhi, Panda, & Sahoo, 2009;O'Connor & Madden, 2006). The employment of the fundamental variables in the ANN environment by various studies include Stock returns, trading volume, and dividends (Kanas & Yannopoulos, 2001), Exchange rates (Walczak, 2001), Accounting ratios (Olson & Mossman, 2003), Portfolio optimization (Ko & Lin, 2008).…”

Section: Literature Reviewmentioning

confidence: 99%

Do the Fama and French Five-Factor Model Forecast Well Using Ann?

Jan

Ayub

2019

Journal of Business Economics and Management

View full text Add to dashboard Cite

Forecasting the stock returns in the emerging markets is challenging due to their peculiar characteristics. These markets exhibit linear as well as nonlinear features and Conventional forecasting methods partially succeed in dealing with the nonlinear nature of stock returns. Contrarily, Artificial Neural Networks (ANN) is a flexible machine learning tool which caters both the linear and nonlinear markets. This paper investigates the forecasting ability of ANN by using Fama and French five-factor model. We construct ANN’s based on the composite factors of the FF5F model to predict portfolio returns in two stages; in stage one, the study identifies the best-fit combination of training, testing, and validation along with the number of neurons full sample period. In stage two, the study uses this best combination to forecast the model under 48-months rolling window analysis. In-sample and out-sample comparisons, regression, and goodness of fit test and actual and predicted values of the stock returns of our ANN model reveal that the proposed model accurately predicts the one-month ahead returns. Our findings reinforce the investment concept that the markets compensate the high-risk portfolios more than mid and low beta portfolios and the methodology will significantly improve the return on investment of the investors.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Do the Fama and French Five-Factor Model Forecast Well Using Ann?

Jan

Ayub

2019

Journal of Business Economics and Management

View full text Add to dashboard Cite

show abstract

“…Research during the last 20 years shows that computational intelligence approaches (more specifically the techniques based on Machine Learning) are more effective in financial time series tasks than analytical approaches [111,59,104,85,93,16,67,116,106,34,63,21,9,64,114,81,61,19,6,55,60,109]. Computational Intelligence includes a wide variety of techniques: Decision trees, Dynamic Bayesian Networks, Hidden Markov Models, Support Vector Machines (SVMs), Kernel methods, Artificial Neural Networks (ANNs), and recently, Deep Learning (DL), which has emerged as a useful technique for asset price modeling.…”

Section: Sniffing Algorithmsmentioning

confidence: 99%

“…Given these characteristics, DL has emerged as a useful technique for asset price modeling because it has proven to be able to learn complex representations of high-dimensional data. Recurrent Neural Network [104] Recurrent Neural Network [85] Feedforward Neural Network + Fuzzy Inference System [93] Recurrent and Probabilistic Neural Networks [16,67] Multilayered Feedforward Neural Network [116] Feedforward Neural Network + Wavelet Transforms [106] Recurrent Neural Networks + GARCH [34] Feedforward Neural Network [63] Neuro-Fuzzy Network [21] Feedforward Artificial Neural Network [9,64] Feedforward Artificial Neural Network [114] Recurrent Neural Network + EGARCH [81] Feedforward Neural Network [61] Recurrent Neural Network [19,6] Feedforward Artificial Neural Network + Genetic Algorithm [55,60] Recurrent Neural Network [109] Recurrent Neural Network [27] Deep Neural Network [36] Artificial Neural Networks + Genetic Algorithms [118] Deep Belief Networks [33] Convolutional Neural Network [22] Long Short-Term Memory [31] Convolutional Neural Networks + Long Short-Term Memory [7] Deep Neural Network [99] Recurrent Neural Network + PCA [12] Long Short-Term Memory + Autoenconders [39] Long Short-Term Memory…”

Section: Artificial Neural Network In Financementioning

confidence: 99%

High-Frequency Trading Strategy Based on Deep Neural Networks

Arévalo

Niño

Hernández

et al. 2016

Intelligent Computing Methodologies

View full text Add to dashboard Cite

Recent conceptual and engineering breakthroughs in Machine Learning (ML), particularly in Deep Neural Networks (DNN), have revolutionized the Computer Science field and have been responsible for astonishing breakthroughs in computer vision, speech recognition, facial recognition, transaction fraud detection, automatic translation, video object tracking, natural language processing, and robotics, virtually disrupting every aspect of our lives. The financial industry has not been oblivious to this revolution; since the introduction of the first ML techniques, there have been efforts to use them as financial modeling and decision tools rendering in some cases limited and other in cases useful results, but overall, not astonishing results as in other areas. Some of the most challenging problems for ML come form finance, for instance, price prediction whose solution will require not only the most advanced ML techniques but also other non-standard and uncommon methods and techniques, giving the origin of a new field called Financial ML, whose name has been coined by Lopez de Prado last year. Today, many hedge funds and investment banks have ML divisions, using all kinds of data sources and techniques, to develop financial modeling and decision tools. Consequently, ML is a part of the present and probably will be the future of the financial industry. In this thesis, we use the Deep Neural Networks (DNN) and Recurrent Neural Networks (RNN), two of the most advanced ML techniques, whose learning capabilities are enhanced using the representational power of the Discrete Wavelet Transform (DWT), to model and predict short-term stock prices showing that these techniques allow us to develop exploitable highfrequency trading strategies. Since high-frequency financial (HF) data are expensive, difficult to access, and immense (Big Data), there is no standard dataset in Finance or Computational Finance. Therefore, the chosen testing dataset consists of the tick-by-tick data of 18 well-known companies from the Dow Jones Industrial Average Index (DJIA). This dataset has 348.98 millions of transactions (17 GB) from January 2015 to July 2017. After a long iterative process of data exploration and feature engineering, several features were tested and combined. The tick-by-tick data are preprocessed and transformed using the DWT with a Haar Filter. The final features consist of the sliding windows of two variables: one-minute pseudo-log-returns (the logarithmic difference between one-minute average prices) and the features generated by the DWT. viii These transformations, which are non-standard data transformations in finance, will better represent the high-frequency behavior of Financial Time Series (FTS). Moreover, the DNN predicts the next one-minute pseudo-log-return that can be transformed into the next predicted one-minute average price. These prices will be used to build a high-frequency trading strategy that buys (sells) when the next one-minute average price prediction is above (below) the last one-minute closing price. Result...

show abstract

“…O'Connor and Madden () used ANNs to predict Dow Jones Industrial Average (DJIA) Index movement using external factors such as commodity prices and currency exchange rates, and reported good results. Dutta et al () used ANNs in an Indian context to forecast the closing price of the Bombay Stock Exchange (SENSEX) and found that ANNs have the ability to predict weekly closing values with good accuracy.…”

Section: Artificial Neural Network Modelling and Literature Reviewmentioning

confidence: 99%

Predicting Next Trading Day Closing Price of Qatar Exchange Index Using Technical Indicators and Artificial Neural Networks

Fadlalla

Amani

2014

Intell. Sys. Acc. Fin. Mgmt.

View full text Add to dashboard Cite

Accurate prediction of stock market price is of great importance to many stakeholders. Artificial neural networks (ANNs) have shown robust capability in predicting stock price return, future stock price and the direction of stock market movement. The major aim of this study is to predict the next trading day closing price of the Qatar Exchange (QE) Index using historical data from 3 January 2010 to 31 December 2012. A multilayer perceptron ANN architecture was used as a prediction model with 10 market technical indicators as input variables. The experimental results indicate that ANNs are an effective modelling technique for predicting the QE Index with high accuracy, outperforming the well-established autoregressive integrated moving average models. To the best of our knowledge, this is the first attempt to use ANNs to predict the QE Index, and its performance results are comparable to, and sometimes better than, many stock market predictions reported in the literature. The ANN model also revealed that the weighted and simple moving averages are the most important technical indicators in predicting the QE Index, and the accumulation/distribution oscillator is the least important such indicator. The analysis results also indicated that the ANNs are resilient to stock market volatility.

show abstract

A neural network approach to predicting stock exchange movements using external factors

Cited by 84 publications

References 6 publications

Do the Fama and French Five-Factor Model Forecast Well Using Ann?

Do the Fama and French Five-Factor Model Forecast Well Using Ann?

High-Frequency Trading Strategy Based on Deep Neural Networks

Predicting Next Trading Day Closing Price of Qatar Exchange Index Using Technical Indicators and Artificial Neural Networks

Contact Info

Product

Resources

About